少来回：结构化提示的比较研究
Less Back-and-Forth: A Comparative Study of Structured Prompting
AI总结：
本文研究了结构化提示设计是否能提高LLM响应质量并减少用户努力，通过比较三种提示条件，发现检查清单提示在任务完成、正确性、合规性和清晰度方面得分最高，且在质量和努力的平衡上表现最佳。
摘要：
大型语言模型（LLMs）广泛用于开放式任务，但不明确的提示可能导致低质量的回答和额外的交互。本文研究结构化提示设计是否能提高响应质量并减少用户努力。我们比较了三种提示条件：原始提示、检查清单改进提示和澄清问题提示。我们通过四个任务类型——摘要、规划、解释和编程，使用三个LLM系统：ChatGPT、Claude和Grok来评估这些条件。每个输出都使用统一的评分标准进行评分，涵盖任务完成、正确性、合规性和清晰度。检查清单改进提示在评分方面得分最高，平均得分为7.50（满分8分），相比原始提示的5.67和澄清问题提示的6.67。检查清单提示在质量和努力的平衡上也表现最佳，使用比原始和澄清提示更少的平均令牌。这些结果表明，简单的提示检查清单可以提高LLM响应质量，同时减少不必要的交互。
英文摘要：
Large language models (LLMs) are widely used for open-ended tasks, but underspecified prompts can lead to low-quality answers and additional interaction. This paper studies whether structured prompt design improves response quality while reducing user effort. We compare three prompt conditions: a raw prompt, a checklist-improved prompt, and a clarifying-question prompt. We evaluate these conditions across four task types--summarization, planning, explanation, and coding--using three LLM systems: ChatGPT, Claude, and Grok. Each output is scored with a unified rubric covering task completion, correctness, compliance, and clarity. Checklist-improved prompts achieved the highest mean rubric score, 7.50 out of 8, compared with 5.67 for raw prompts and 6.67 for clarifying-question prompts. Checklist prompts also produced the best quality-effort tradeoff, using fewer average tokens than both raw and clarifying prompts. These results suggest that a simple prompt checklist can improve LLM responses while reducing unnecessary interaction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
